Triple
T18353839
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Murder of Laura Foster |
E439737
|
entity |
| Predicate | hasDisputedAspects |
P14608
|
FINISHED |
| Object | identity of the true killer |
—
|
LITERAL FINISHED |
How this triple was built (2 steps)
Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.
NER
Named-entity recognition
gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: identity of the true killer | Statement: [Murder of Laura Foster, hasDisputedAspects, identity of the true killer]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasDisputedAspects Context triple: [Murder of Laura Foster, hasDisputedAspects, identity of the true killer]
-
A.
disputedAspect
chosen
Indicates that a particular feature, detail, or component of something is subject to disagreement or contention between parties.
-
B.
hasDisputedStatus
Indicates that the status or classification of something is contested, uncertain, or not universally agreed upon.
-
C.
hasDisputedStatusWith
Indicates that there is a contested or unresolved status, claim, or standing between the related entities.
-
D.
hasDisputedClause
Indicates that a particular clause within an agreement or document is subject to disagreement, challenge, or contention between involved parties.
-
E.
hasDisputeWith
Indicates that there is a conflict, disagreement, or contested issue between two entities.
- F. None of above.
Provenance (3 batches)
The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.
| Step | Stage | Batch ID | Status | When |
|---|---|---|---|---|
| creating | Elicitation | batch_69d8b918221c8190a9f7b563d64ac677 |
completed | April 10, 2026, 8:47 a.m. |
| NER | Named-entity recognition | batch_69e516d37bc08190abc9b4e8c937c914 |
completed | April 19, 2026, 5:54 p.m. |
| PD | Predicate disambiguation | batch_69e44fe91bc08190906518e1b120fcf0 |
completed | April 19, 2026, 3:45 a.m. |
Created at: April 10, 2026, 10:37 a.m.